← Back to Explore

High-Resolution Super sampling of BASP-ORCA Contrast Agents in Magnetic Resonance Imaging

JSHS · 2024

Overview

Magnetic Resonance Imaging (MRI) is crucial in clinical diagnostics, but traditional metal-based contrast agents have toxicity concerns. When nearly 1 in 7 Americans suffer from some class of Chronic Kidney Disease traditional contrast agents pose a risk to their health due to heavy metal toxicity. Brush-Arm Star Polymer Organic Radical Contrast Agents (BASP-ORCAs), a new metal-free class, enhance MRI by providing better transverse relaxivity and stability, reducing health risks from conventional agents. The research evaluates deep learning models, specifically convolutional neural networks and hybrid attention transformers, for improving MRI scan resolution. These models are trained on nearly three hundred T1 and T2 MRI images, mainly sourced from the IXI dataset and supplemented with BASP-ORCA scans. Images are downscaled so that they can be trained against their high resolution counter parts. The models are meant to learn complex patterns to enhance image quality. This results in sharper, more detailed images, crucial for tumor detection and characterization. The model achieved a Structural Similarity Index Measure of 0.92 and a Peak Signal-to-Noise Ratio of 33.13, showing its effectiveness. Combining BASP-ORCAs with advanced computational techniques could improve diagnostic accuracy and patient safety, signifying a shift towards non-toxic radiology solutions. Washington

Competition history

  • JSHS 2024 Category not listed

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Source: Junior Science and Humanities Symposium

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google